A Two-Stage Risk-Averse DRO-MILP Methodological Framework for Managing AI/Data Center Demand Shocks

TL;DR

This paper introduces a two-stage risk-aware optimization framework for managing AI-driven demand shocks in power systems, enhancing resilience through coordinated pre- and post-event strategies.

Contribution

It presents a novel DRO-MILP approach that integrates risk considerations into planning and real-time response for AI-related demand surges in distribution grids.

Findings

Effective pre-allocation of FCMs under uncertainty

Improved real-time stabilization after demand shocks

Scalable framework applicable to larger power systems

Abstract

The rapid growth of artificial intelligence (AI)-driven data centers is reshaping electricity demand patterns. This is achieved by introducing fast, multi-gigawatt load ramps that challenge the stability and resilience of modern power systems. Traditional resilience frameworks focus mainly on physical outages and largely overlook these emerging digital-era disturbances. This paper proposes a unified two-stage, risk-aware distributionally robust optimization (DRO)-MILP framework that coordinates the pre-allocation and post-event dispatch of Flexible Capacity Modules (FCMs), including BESS, fast-ramping generation, demand response, and potential long-duration storage. Stage-I optimally positions FCMs using DRO with CVaR to hedge against uncertain AI load surges. Stage-II models real-time stabilization following stochastic demand-shock scenarios, minimizing imbalance, unserved energy, and restoration penalties. The framework is designed to be applied on IEEE 33-bus system or expanded for scalability to larger IEEE test feeders capable of representing AI-scale loads. This contributes a scalable planning tool for resilient, AI-integrated distribution grids.